Learning Depthwise Separable Graph Convolution from Data Manifold
arXiv preprint arXiv:1710.11577, 2017.
Abstract:
Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending convolution operations to the non-Euclidean geometry. Although various types of convolution operations have been proposed fo...More
Code:
Data:
Tags
Comments